Back to Index

Startups building new products with Claude | Code w/ Claude


Transcript

welcome welcome everyone i'm joe i'm from the startups team here at anthropic and we're so thrilled to have all of you here today we have a breakout of six amazing founders that have really found product market fit building on cloud across a bunch of different industries across agentic coding across design across music generation and a lot of these startups have really seen that zero to multi-million user journey within the past 12 months and i know in this crowd there's a lot of you know really great founders too and so we want all of you to stay until the end of the session we have a little surprise for all of you to be able to spin up quicker uh on claude four um in our new family of models so without further ado i want to bring up kevin uh who is the ceo and co-founder of tempo labs awesome thanks joe everyone nice to meet you as she mentioned my name is kevin one of the co-founders of tempo and it's an honor to be here i'm to kick off i have a video uh that'll give you a little bit of a taste of what temple is all about so awesome so uh what is tempo at tempo we're building cursor for pms and designers uh tempo is a new type of ide that feels more like a design tool like figma than it does vs code and the whole idea behind it is to to give designers and pms the ability to collaborate with claude uh and to create you know the first draft of pull requests and in many cases uh the actual end-to-end pull request uh kind of pulling the engineer out of the loop in some cases but if anything making the process of working on code collaborative as it stands today it's really non-engineers don't you know collaborate too much on code so i'll show you a bit of a live demo of what that looks like uh this is tempo uh tempo as you can tell uh you know has three tabs product uh a prd tab a design tab and a code tab so imagine you're a pm right you generate uh airbnb app with uh claude and you're like okay great this looks you know it's a it's a it's a quick and dirty prototype demo uh and then you pass it off to your designer and your designer looks at uh the real airbnb and it's kind of like hmm this is kind of off i need to get it pixel perfect so uh you come in in here and you realize that uh you know you spent some time working on this new animated uh tabs header so you can see you know just like the it's nice and pretty just like the core uh airbnb uh so what i can do now is i can uh drag and drop this right into my header over here uh give that a second there you go we've got it in the header uh and then what i can do is just rearrange this to get it in the middle um and again every change that i'm making is actually you know you can see editing the original source code in the correct position um so okay so we're kind of like starting to make some progress now clearly these little new badges are not great you know whenever whoever designed or created that didn't do a great job so why don't we fix that up really quick um so i'm going to open up my uh dom tree over here which shows me everything that's in the dom i'll find the new badge and i'll just click delete just like i would boom okay we're getting somewhere close looks you know half decent now let's compare to airbnb okay we've got some work to do clearly claude thought we need this little text header i'm just going to delete that like i normally would in a design tool traditional design tool like figma i'm going to delete this over here and then i am going to let's compare again i'm going to move my uh the ellen to my property grid here to the center i'm going to add a little bit of gap between them and then maybe here i'm going to remove this uh tailwind padding and then i'm going to compare to core airbnb and then the site that i built in tempo and now you get an idea of how you know pms designers can collaborate together with claude and then again i can enter a commit message push this to uh to github and actually the really cool thing is that this actually this code isn't running locally on my machine it's actually running on a docker container in the cloud so this whole thing is collaborative i can send a link to someone just like figma and they can come and collaboratively code with me and with claude there you go tempo is again it's an ide for designers and developers uh to collaborate together on code we already have a number of customers and have been growing extremely extremely quickly uh and what we're seeing for customers that adopt tempo is designers truly are turning into design engineers and we're seeing that you know approximately 10 to 15 percent of front-end pull requests are actually being able to be opened by designers directly they're often able to do pixel pushing themselves without involving an engineer they can just work with tempo and with claude directly and in in about 60 percent of pull requests we see that a a sizable chunk of the front-end code has been generated by designers by pms and by claude and it actually accelerates it's useful code that accelerates a true front-end engineer uh in their process of going to production and so that's tempo we are in the we're imminently about to release support for claude 4 so i invite you all to uh give it a shot uh and uh empower your pms and your designers to start to collaborate with your engineers on code thank you howdy everybody um my name is andrew file i will start uh with a little bit of a past history i build and sold software business for more than two billion dollars so i ran a team of more than thousand people and despite doing that i could tell that only about two to five percent of our ideas ever came to life because the majority of the time we spend on fairly routine work and the larger is the company the more of that routine is in your uh kind of uh the the bigger that routine makes part of your of your day job so i fundamentally believe that uh we can automate at least 90 percent of that routine work giving us opportunity to move 10 times faster and bring more of our ideas to life and um i personally uh believe that a lot of their of this transformation will happen this year and we're uh actually observing it as we speak including today i think that uh this week actually demark demarks their transition into the next generation so how only 12 months ago the whole industry was on the first generation of ai coding assistance so a code completion it kind of uh was a very nice convenience but not a game changer to to anybody and then october last year um thanks to entropic we got um cloud 3.5 and that was a game changer and that allowed um us and zencoder and uh cursor and windsurf and a lot of other players to build true coding agents inside of your id so that opened up a completely new uh use cases completely new scenarios we saw usage skyrocket uh 10x 100x and we saw people uh being able to do amazing things that they haven't been able to do before and part of that revolution was um the model support for tools and environment because behind a lot of those generational changes there are some technical capabilities that kind of unlock all of that right uh there was also move in the models from coding quote unquote like olympiad style stuff to true software engineering and that was uh very very very important and then uh obviously context matters um software repositories are quite large so it's good to to have a larger support and i think that uh in this year we'll actually see transition to the next generation uh for me one of the biggest enablers there is verification uh so i'm super excited about something that we haven't yet talked uh at this conference today is computer use we saw rapid progress in those models and they allow us to build uh proper verification and verification is key to scaling ai uh and kind of delivering more fully autonomous cycle and then the other thing is uh in real life in actual uh production work uh where you got multiple people engaged and multiple teams engaged uh typically a lot of the time is wasted doing what i call in between uh kind of passing the ball and so when we think about the problem we think about software development life cycle as a whole uh not just about the coding and that's a big part of our dna and so super happy to announce a couple of weeks ago uh came with zen agents so taking that concept of um coding agent and extending into custom agents that you can share across your whole organization with full support for mcp with specialized coding tools and whatnot but you can basically deploy them across your whole sdlc from their uh work on your prd to to the actual coding to verification to code reviews and whatnot so that's super exciting and i'll just basically show you a quick video and we'll be good to go and we're looking forward for entropic to bring us mcp registry uh but while that's not available we offer you ours so we got a hundred um i believe about 100 mcp servers out there and obviously you can configure your own and also as we launched that zen agents we were excited to launch the community aspects of it so there's an uh mit licensed github repo where you can commit your agents and if we approve your pr uh everybody will will see them so we're excited and think that that can help kickstart the creativity process in a lot of organizations and kind of take it beyond the basic coding use uh truly across the whole software development life cycle so thank you all hi my name is jordan i'm the head of ai engineering at gamma and at gamma our mission is to help bring your ideas to life whether that's presentations documents websites or even social media carousels we do all this so we can help us through ai to help build these things for you and we love quad uh throughout gamma's kind of history of using ai there's been two moments where a model upgrade has made significant impact to our key metrics around user satisfaction for deck generation the first was when sonnet 3.5 came out and the second was when sonnet 3.7 came out we actually saw an eight percent increase in this metric which is something that we spent hundreds of hours trying to prompt engineer around and could not get such improvements and one of the big reasons for this was around web search so the built-in tool in sonnet that we can natively use web search for and not have to use the third-party service so i'm going to show you the difference what web search made in gamma by showing two decks generated with gamma one with web search and one without so this is gamma gamma used ai to generate this it used sonnet 3.7 but it did not use web search and as you can see got a lot of things wrong this conference isn't january 22nd 2025 it's not three days i don't think these are the right speakers so let's see what we can do with web search so in gamma you can create a entire presentation web page document anything from a single sentence so i'll type in code with claude conference 2025 and it's going to first create an outline for me it's going to search the web to figure out what should be in this outline and it will inevitably find details about the code with claude conference and put them there so as you can see we're already off to a better start where we have the correct dates we have real technical sessions we have the right location so this looks much better for us and i've even gone ahead and created an an anthropic theme that we can use so now that we have the outline generated gamma will take that outline and it will take the other information it has and create an entire presentation for us with hopefully the correct details so let's check so i think already we're off to a better start it has the right date has the right location it tells us the schedule and overall this provides us a much better starting point if we were to say make a presentation or a website about this conference it's not going to be perfect but it'll get you to a point where you have the correct information and you're at a good starting point to actually finish your presentation so this one change from sonnet 3.5 to 3.7 with with web search was a huge lift for us and we're very excited to continue to use claude and to continue to see these improvements lastly we are hiring so if you are an engineer or product or designer and are interested in working at gamma you can go to careers.gamma.app thank you hi my name is amar goyal i'm the ceo and co-founder of bitto we're building the hopefully the world's best ai code review platform so as we all know we're using all these cursor windsurf cloud cloud code to write massive massive amounts of code the amount of code that developers are writing we think is going to go up 10x over the next year or two but what that means is that you know vibe coding which we all talk about does not equal vibe engineering how do you get code that's scalable reliable performant fits into your architectural design patterns and that's still left to the code review process but code review is not going to scale teams have trouble keeping up today it's not going to scale for 10x the amount of code bitto's built an ai code review that plugs into github gitlab bitbucket works with over 50 languages our focus is really especially with sonnet having a really high quality model that provides a human-like code review focuses on the critical things our biggest thing is really about more signal and less noise how do we provide you actionable important suggestions let me show it to you so we've got a pr here this is gitlab that works kind of the same in all the platforms so once you create a pr bitto's fired bitto gets called and we first start by summarizing your pr this doesn't require any documentation or any comments we just look at the diffs we look at your code and we summarize it then we give you a quick kind of overview of what we found in the pr so here we found three actionable suggestions some things about missing resources a cache implementation that needs to be impacted and then a class cast exception error which we'll talk about next we provide a change list this change list gives you it's kind of a double click on the summary summarizes the key changes in your pr and then looks at what are the diffs that comprise that so you as a reviewer you get a quick double click on what actually matters in this pr now let's go through a couple of these suggestions so this first one is really about this resource management resource manager class is talking about a permanent resource leak if you don't fix this so we give you a detailed code suggestion which you can then one click apply as a commit or you can batch those commits the next suggestion that we'll look at really briefly is this non-thread safe static cache implementation and so we again we've given you a code suggestion we're suggesting a concurrent hash map instead of a hash map to avoid race conditions now let's talk a little bit about this third suggestion which i think is really important and highlights how we use sonnet so we really use sonnet to provide that human-like code review and those reasoning capabilities we've done a lot of work to really understand your code base and that's where sonnet kind of comes in so if you look here what we've got is this network data fetcher class it has been cast to a link list this is java if you're not familiar with java i'll just kind of walk you through it but really what's happening here is that this data uh you can see there's a data processor constructor that then cast something to an array list which is going to cause a class cast exception in production now how did the how did we find this well what bido has done is that it looked through the code and said hey for this network data fetcher you were trying to instantiate this data processor object this data processor object then well what is that we went and looked crawled your code understood it through abstract syntax trees a symbol index and sonnets reasoning and said hey this is cast as an array list and so now this array list you know is going to collide with this link list and going to create an exception in production this is probably an error that most humans wouldn't even find let alone you know most systems now if we want to shift this left we can even bring this to your ide so here's the same changes in your ide you can easily kind of right click and say hey i want to review my local changes stage commits etc run review those local changes the same agent runs in your ide again being driven by sonnet um and we provide the the output and then you can one click apply those suggestions uh so that's uh that's a little bit about how it how it works uh maybe i'll just mention one last thing so we have hundreds of customers and you know the question is well what impact is this really having so prs are closing in one-tenth a time so that pr that used to close take 50 hours to go from open to merge now goes open to merge in five hours these are three companies hundreds of engineers and bito's providing 80-ish percent of the feedback that a pr receives so we're taking care of the vast majority of the work and it's really being driven by the fact that ai provides that feedback in three minutes or four four minutes instead of one or two days thank you let's talk about something different so my name is hike and i want to talk about refusion so refusion is a generative music startup here in san francisco and we work on training frontier music models and then create an incredible product experience for crafting and exploring the art of music and our song lyrics writing pipeline is powered by claude so our core thing that we train is a diffusion transformer we train this from scratch and we think it's the most creative music model in the world we train it for quality for diversity for speed for controllability and as a fun anecdote this square of pixels here represents 30 seconds of music in our latent space um it's kind of crazy to think about how compressed that is but uh writing fantastic song lyrics is a crucial part of great songs um and current llms are um good at a very many things but writing good song lyrics they're they're still pretty cringy um but claude is the best for sure and we built an agent called ghostwriter that's essentially meant to help you write and refine song lyrics as an artist and basically focusing on you know diversity humor taste what flowing with the music itself and this is a crucial tool um in our product uh it's been used tens of millions of times now to to write song lyrics so let's go demo some stuff if we pop over to my computer so this is our home page refusion.com check it out it's really fun there's a lot of amazing music to explore on here um i will just punch in something here uh let's say experimental indie trip hop about the feeling of getting better after being really sick there's a song concept pop in a couple of those um in the meantime let me just play a song and there's a there's a ton of really deep editing workflows here for getting in stuff but also just getting started you can just type something in and start listening to music and go from there so let me just play a song from the the home page and then we'll go back and listen to what we made don't downplay my brine i've been clocking kills since the ink dried on that line you ain't copping these souls now limited supply too many laws left cold in the breeze then they mama selling gumbo just to cover the fees please flip the corner cash the equity that's the creed but most is crashing out living life on the speed in the dry cool breeze thick hair like alicia keys told god your manifest me queen take it out fill the closet let us stun on the scene but i'm cut different ain't a rapper who i run my steez news all right so let's listen to some of the songs here we've got the reawakening let's see what the lyrics look like here written by a ghostwriter with claude my muscles forgot what they're meant to do the ceiling fan spins in slow motion while i gather strength to move fingertips press against the mattress testing if i can hold my way pretty good let's see dawn fade so whenever ghostwriter generates we have uh kind of an iterative process of thinking about the concept of a song ideating about actually the context of the genre you're writing for because say the lyrics of a drum and bass song are super different the lyrics of a you know a folk song that might be storytelling um and that process of just trying to get something that actually fits with the music is actually really hard and subtle and requires a lot of iteration and refinement so an example of some of the kind of deep editing stuff we can do here so we can do remixing to create variations to extend from a certain section to replace a section actually to swap the stems like the vocals and the sound while keeping the other one the same and even capturing this idea of a vibe which is like a short audio snippet that you can then use the prompt instead of text so you can mix and match these things and just get really deep in your refinement and then with ghostwriter let's say if we were to use a prompt here um we were to use the lyrics here actually throw them up then we could type in here like add a spoken word intro in french and just pop that in and start start iterating so yeah that's the that's the app and the product and it's it's a really fun experience and um claude's claude's definitely the best for this kind of stuff so yeah come talk to me come talk to henry if you're interested in music and uh thanks um hey everyone i'm drew from the co-founder and ceo of create uh we're an ai text to app builder that lets anybody build working software products um on the internet and uh the exciting thing about create is it's an ai agent that can take in just natural language prompts and go end to end uh on building things so we got our start in web apps and claude is one of the base models that powers a lot of our code writing for the agent um but we're really excited about um our new mobile app builder that is for the first time letting people actually build mobile apps and so today i thought i'd just go ahead and show it off so i'll switch over to the live demo um and we're in beta but uh somebody just actually emailed me an idea a few weeks ago for a family memory app that lets people uh basically store their memories on their phones uh upload their uh different images and oops live demos uh store their different images and uh get going on building their family memory app so let me actually go create a new project and type this in and say make an ios app for this and as you type creates agent starts getting to work um it's going to start building out all the core pages um as well as the back-end functionality for what you need um and so it will also pull in other integrations you can you might need to use um and go ahead and get set up i uh i am actually going to go ahead and switch to some pre-loaded things so the basic idea is you prompt uh and you're able to actually generate full applications um the cool thing about create oh there we go starting to build a little bit um is that um it also comes built in with back-ends and front-ends and everything you kind of need from the uh from the database to the actual core off um and so here it's actually building out my family memory's front-end but then in a second you'll see that also issues the like schemas uh for the database and goes ahead and deploys a full database and hooks up all the functions needed to talk to this front-end we are really excited about the fact that non-technical users in the hundreds of thousands are starting to pour into create to actually fully build apps um without needing to go to the id and truly just work from prompt land um and so one of the biggest things that we've been working on is actually the ability to also fully submit from create as well um create after your app is done then goes ahead and submits your app straight to the app store and builds a build for you um there's actually an app we built uh in a day um you can just in one click publish it and submit to the app store and this will go ahead and kick off a build um we actually already started uh got this app in the app store so if anyone here wants to download it and play with it it's an ai app that lets you very quickly take drawings and turn it into uh ai images called draw daily um and then in the beta the thing that's been the most exciting uh for us is just seeing all the cool apps that are being created so we just hosted a demo day and this is william and he is making an app to help you memorize meaningful connections and details of people's lives and pull it up and so you just talk to the app and it pulls up special information about your contact info and and helps you remember anything for sales calls or anything else you want or we also had a student at berkeley who's building the scholarship app that he's always wanted um where he's constantly filling out grants um and unable to kind of do it automatically and so he's building scholar gpt and a lot of these like the core agent of how they built we're using you know prompt caching tool calling a lot of the core primitives that anthropic makes available to actually get them to success and just to show a few more um blaze is actually a basketball coach and for the first time ever he's using create to get rid of all of these spreadsheets and drills he does for his uh coaches and instead uh you build a full player coach app that lets them uh download uh drills uh put their lesson plan out and then uh see animations on in the app of how they uh should be uh getting used and then finally uh we've also had personal finance apps being created um so like a personal ai money coach for gen z with full rag um that also has a claude powered uh assistant that can figure out your monthly income and give you personalized financial recommendations and so part of what we were like most excited about is just the explosion of who and how uh software will be made um when you give people of these tools and very excited to partner with uh claude to power all of this thank you Thank you.

Thank you.